{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XAR2GEW7D3WNGGM3JFLRXOQLYJ","short_pith_number":"pith:XAR2GEW7","schema_version":"1.0","canonical_sha256":"b823a312df1eecd3199b49571bba0bc27c2e640d4e074efcc2ca0928940bb8f7","source":{"kind":"arxiv","id":"2405.10314","version":1},"attestation_state":"computed","paper":{"title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksander Holynski, Arthur Brussee, Ben Poole, Jonathan T. Barron, Philipp Henzler, Pratul Srinivasan, Ricardo Martin-Brualla, Ruiqi Gao","submitted_at":"2024-05-16T17:59:05Z","abstract_excerpt":"Advances in 3D reconstruction have enabled high-quality 3D capture, but require a user to collect hundreds to thousands of images to create a 3D scene. We present CAT3D, a method for creating anything in 3D by simulating this real-world capture process with a multi-view diffusion model. Given any number of input images and a set of target novel viewpoints, our model generates highly consistent novel views of a scene. These generated views can be used as input to robust 3D reconstruction techniques to produce 3D representations that can be rendered from any viewpoint in real-time. CAT3D can cre"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.10314","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-16T17:59:05Z","cross_cats_sorted":[],"title_canon_sha256":"b4f2932b7831938d7dd1cd4c20c7a5c414fe922a8e09d6afdc4f88e6978af4ea","abstract_canon_sha256":"fdd1d8fc65a58c29188510c5159efaa30f918d8460fc0b24c637cf89c554e0e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-19T21:23:17.390058Z","signature_b64":"WxXs8dC+10TXe9WfqYe7fHmkI/tJpIanli+iBDxCbfUNLjLD35U7YY2kV7+dQWRDRoGFyIS38NLFqiS/2Ek+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b823a312df1eecd3199b49571bba0bc27c2e640d4e074efcc2ca0928940bb8f7","last_reissued_at":"2026-05-19T21:23:17.388267Z","signature_status":"signed_v1","first_computed_at":"2026-05-19T21:23:17.388267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksander Holynski, Arthur Brussee, Ben Poole, Jonathan T. Barron, Philipp Henzler, Pratul Srinivasan, Ricardo Martin-Brualla, Ruiqi Gao","submitted_at":"2024-05-16T17:59:05Z","abstract_excerpt":"Advances in 3D reconstruction have enabled high-quality 3D capture, but require a user to collect hundreds to thousands of images to create a 3D scene. We present CAT3D, a method for creating anything in 3D by simulating this real-world capture process with a multi-view diffusion model. Given any number of input images and a set of target novel viewpoints, our model generates highly consistent novel views of a scene. These generated views can be used as input to robust 3D reconstruction techniques to produce 3D representations that can be rendered from any viewpoint in real-time. CAT3D can cre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10314","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.10314/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.10314","created_at":"2026-05-19T21:23:17.388346+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10314v1","created_at":"2026-05-19T21:23:17.388346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10314","created_at":"2026-05-19T21:23:17.388346+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAR2GEW7D3WN","created_at":"2026-05-19T21:23:17.388346+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAR2GEW7D3WNGGM3","created_at":"2026-05-19T21:23:17.388346+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAR2GEW7","created_at":"2026-05-19T21:23:17.388346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":24,"sample":[{"citing_arxiv_id":"2605.23888","citing_title":"GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2412.13111","citing_title":"Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20155","citing_title":"GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Seconds","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18365","citing_title":"GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16807","citing_title":"DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16990","citing_title":"DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16873","citing_title":"HAD: Hallucination-Aware Diffusion Priors for 3D Reconstruction","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2505.21996","citing_title":"VRAG: Learning World Models for Interactive Video Generation","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2603.11911","citing_title":"InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12938","citing_title":"CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2409.02048","citing_title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02828","citing_title":"NavCrafter: Exploring 3D Scenes from a Single Image","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20155","citing_title":"GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Seconds","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20093","citing_title":"FurnSet: Exploiting Repeats for 3D Scene Reconstruction","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18468","citing_title":"Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12309","citing_title":"Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11331","citing_title":"Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08500","citing_title":"Novel View Synthesis as Video Completion","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14302","citing_title":"Geometrically Consistent Multi-View Scene Generation from Freehand Sketches","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14025","citing_title":"Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective","ref_index":253,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20784","citing_title":"GeoRect4D: Geometry-Compatible Generative Rectification for Dynamic Sparse-View 3D Reconstruction","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XAR2GEW7D3WNGGM3JFLRXOQLYJ","json":"https://pith.science/pith/XAR2GEW7D3WNGGM3JFLRXOQLYJ.json","graph_json":"https://pith.science/api/pith-number/XAR2GEW7D3WNGGM3JFLRXOQLYJ/graph.json","events_json":"https://pith.science/api/pith-number/XAR2GEW7D3WNGGM3JFLRXOQLYJ/events.json","paper":"https://pith.science/paper/XAR2GEW7"},"agent_actions":{"view_html":"https://pith.science/pith/XAR2GEW7D3WNGGM3JFLRXOQLYJ","download_json":"https://pith.science/pith/XAR2GEW7D3WNGGM3JFLRXOQLYJ.json","view_paper":"https://pith.science/paper/XAR2GEW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10314&json=true","fetch_graph":"https://pith.science/api/pith-number/XAR2GEW7D3WNGGM3JFLRXOQLYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XAR2GEW7D3WNGGM3JFLRXOQLYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAR2GEW7D3WNGGM3JFLRXOQLYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAR2GEW7D3WNGGM3JFLRXOQLYJ/action/storage_attestation","attest_author":"https://pith.science/pith/XAR2GEW7D3WNGGM3JFLRXOQLYJ/action/author_attestation","sign_citation":"https://pith.science/pith/XAR2GEW7D3WNGGM3JFLRXOQLYJ/action/citation_signature","submit_replication":"https://pith.science/pith/XAR2GEW7D3WNGGM3JFLRXOQLYJ/action/replication_record"}},"created_at":"2026-05-19T21:23:17.388346+00:00","updated_at":"2026-05-19T21:23:17.388346+00:00"}